AI Evaluation Architect for Data Science Quality

Mercor; Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

Mercor is partnering with a leading AI research organization to engage experienced data scientists for a project focused on evaluating how well AI systems perform real-world data science work. You will define what excellent work looks like: designing task-specific grading criteria and scoring completed work samples with rigorous, well-reasoned written justifications.

Key responsibilities include designing grading criteria, scoring both AI-generated and human samples, applying evidence-based

Qualifications

• 5+ years of professional data science experience in industry.
• Deep fluency in experiment design and A/B testing.
• Strong ability to define metrics and communicate findings to executives.
• Detailed written communication and clear justification of scores.

Responsibilities

• Design precise, task-specific grading criteria for real-world data science deliverables.
• Score AI-generated and human work samples with detailed written justifications.
• Apply evidence-based judgment to ensure scores are reproducible and defensible.
• Incorporate feedback from senior reviewers and iterate quickly.

Skills

Data science

Experiment design

A/B testing

SQL

Python

Executive communication

Job description

Mercor is partnering with a leading AI research organization to engage experienced data scientists for a project focused on evaluating how well AI systems perform real-world data science work. You will define what excellent work looks like: designing task-specific grading criteria and scoring completed work samples with rigorous, well-reasoned written justifications.

Key responsibilities include designing grading criteria, scoring both AI-generated and human samples, applying evidence-based